INDEX

Explanations

statements related to negative impacts or detrimental outcomes in scientific contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.60

 synced

-0.53

Bar

-0.49

 Barry

-0.48

 professional

-0.47

…

-0.47

ManyToOne

-0.46

 Personal

-0.46

ومة

-0.45

 hears

-0.45

POSITIVE LOGITS

setVerticalGroup

1.14

 CreateTagHelper

1.02

GraphicsUnit

0.97

tagHelperRunner

0.93

 InputDecoration

0.90

MemoryWarning

0.89

WriteTagHelper

0.85

 незавершена

0.83

archiviato

0.81

 AssemblyCulture

0.81

Activations Density 3.444%

statements related to negative impacts or detrimental outcomes in scientific contexts

No Comments

No Known Activations